{"title":"Boosting for Distributed Online Convex Optimization","authors":"Yuhan Hu;Yawei Zhao;Lailong Luo;Deke Guo","doi":"10.26599/TST.2022.9010041","DOIUrl":null,"url":null,"abstract":"","PeriodicalId":60306,"journal":{"name":"Tsinghua Science and Technology","volume":"28 4","pages":""},"PeriodicalIF":5.2000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/5971803/10011153/10011174.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tsinghua Science and Technology","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10011174/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
分布式在线凸优化的Boosting
去中心化在线学习(DOL)将在线学习扩展到分布式网络领域。然而,与集中式方法相比,分散环境中本地数据的局限性导致决策或模型的准确性下降。考虑到在网络中使用分布式数据资源实现高精度模型或决策的要求越来越高,尝试应用集成方法来仅通过传递梯度或模型来实现优越的模型或决策。设计了一种新的boosting方法,即分布式在线凸优化boosting(BD-OCO),以实现boosting在分布式场景中的应用。BD-OCO达到后悔上界$\mathcal{O}\left(\frac{M+N}{MN}T\右)$,其中$M$测量分布式网络的大小,$N$是每个节点中的弱学习者(WL)的数量。BD-OCO的核心思想是应用局部模型来训练一个强大的全局模型。BD-OCO基于八个不同的真实世界数据集进行评估。数值计算结果表明,BD-OCO在精度和收敛性方面都取得了良好的性能,并且对分布式网络的大小具有鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。